Scribd
Upload
13 views

1.4 Data Science Topic 2

Uploaded by

chsscm1
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
13 views

1.4 Data Science Topic 2

Uploaded by

chsscm1
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 11

Data science topics

Objectives
 Foundations of Artificial Intelligence
 Understand Machine Learning
 Understand Deep Learning
 The comparison between Machine Learning and Deep
Learning

Introduction 2
Artificial Intelligence
 John McCarthy: " It is the science and engineering of
making intelligent machines, especially intelligent
computer programs. It is related to the similar task of
using computers to understand human intelligence, but AI
does not have to confine itself to methods that are
biologically observable.”
 Artificial intelligence: combines computer science and
robust datasets, to enable problem-solving.
 Sub-fields of machine learning and deep learning, which
are frequently mentioned in conjunction with artificial
intelligence.
 AI algorithms which seek to create expert systems which
make predictions or classifications based on input data.

3
Artificial Intelligence
 Artificial intelligence applications
 Speech recognition: It is also known as automatic
speech recognition (ASR), computer speech recognition, or
speech-to-text, and it is a capability which uses natural
language processing (NLP) to process human speech into a
written format.
 Customer service: Online virtual agents are replacing
human agents along the customer journey.
 Computer vision: enables computers and systems to
derive meaningful information from digital images, videos
and other visual inputs, and based on those inputs, it can
take action.

4
Artificial Intelligence
 Artificial intelligence applications
 Recommendation engines: Using past consumption
behavior data, AI algorithms can help to discover data
trends that can be used to develop more effective cross-
selling strategies.
 Automated stock trading: Designed to optimize stock
portfolios, AI-driven high-frequency trading platforms make
thousands or even millions of trades per day without
human intervention.

5
Machine Learning
 Machine learning is a branch of artificial intelligence (AI)
and computer science which focuses on the use of data
and algorithms to imitate the way that humans learn,
gradually improving its accuracy.
 Machine learning is an important component of the
growing field of data science.
 Through the use of statistical methods, algorithms are
trained to make classifications or predictions,
uncovering key insights within data mining projects.
 These insights subsequently drive decision making
within applications and businesses, ideally impacting
key growth metrics

6
Deep Learning
 Deep learning is a subset of machine learning, which is
essentially a neural network with three or more layers.
 These neural networks attempt to simulate the behavior
of the human brain—albeit far from matching its ability
—allowing it to “learn” from large amounts of data.
 While a neural network with a single layer can still make
approximate predictions, additional hidden layers can
help to optimize and refine for accuracy.
 Deep learning drives many artificial intelligence (AI)
applications and services that improve automation,
performing analytical and physical tasks without human
intervention.

7
What's the difference?
Factors Deep Learning Machine Learnig

Data Requirement Requires large data Can train on lesser


data
Accuracy High Lesser accuracy

Training time Longer to train Less time to train

Hardware Requires GPU to Train om cpu


Dependency train
Hyperparameter Can be turned in Limited tuning
Tuning various different capabilities
ways

8
What's the difference?
Factors Deep Learning Machine Learnig
Types - Supervised learning - Convolutional neural
- Unsupervised networks
learning - Recurrent neural
- Reinforcement networks
learning
General Deep learning Machine learning uses
structures algorithms in algorithms to parse data,
layers to create an learn from that data, and
“artificial neural make informed decisions
network” that can learn based on what it has
and make intelligent learned.
decisions on its own.

9
Summary
 Foundations of Artificial Intelligence
 Understand Machine Learning
 Understand Deep Learning
 The comparison between Machine Learning and Deep
Learning

Introduction 10
Q&A

11

You might also like